서브메뉴
검색
Incorporating Human Plausibility in Single- and Multi-agent AI Systems
Incorporating Human Plausibility in Single- and Multi-agent AI Systems
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151424
- ISBN
- 9798382806792
- DDC
- 004
- 서명/저자
- Incorporating Human Plausibility in Single- and Multi-agent AI Systems
- 발행사항
- [Sl] : Princeton University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 103 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
- 주기사항
- Advisor: Adams, Ryan P.;Griffiths, Tom.
- 학위논문주기
- Thesis (Ph.D.)--Princeton University, 2024.
- 초록/해제
- 요약As AI systems play a progressively larger role in human affairs, it becomes more important that these systems are built with insights from human behavior. In particular, models that are developed on the principle of human plausibility will more likely yield results that are more accountable and more interpretable, in a way that greater ensures an alignment between the behavior of the system and what its stakeholders want from it. In this dissertation, I will present three projects that build on the principle of human plausibility for three distinct applications:(i) Plausible representations: I present the Priority-Adjusted Reply for Successor Representations (PARSR) algorithm, a single-agent reinforcement learning algorithm that brings together the ideas of prioritization-based replay and successor representation learning. Both of these ideas lead to a more biologically plausible algorithm that captures human-like capabilities of transferring and generalizing knowledge from previous tasks to novel, unseen ones.(ii) Plausible inference: I present a pragmatic account of the weak evidence effect, a counterintuitive phenomenon of social cognition that occurs when humans must account for persuasive goals when incorporating evidence from other speakers. This leads to a recursive, Bayesian model that encapsulates how AI systems and their human stakeholders communicate with and understand one another in a way that accounts for the vested interests that each will have.(iii) Plausible evaluation: I introduce a tractable and generalizable measure for cooperative behavior in multi-agent systems that is counterfactually contrastive, contextual, and customizable with respect to different environmental parameters. This measure can be of practical use in disambiguating between cases in which collective welfare is achieved through genuine cooperation, or by each agent acting solely in its own self-interest, both of which result in the same outcome.
- 일반주제명
- Computer science
- 일반주제명
- Computer engineering
- 키워드
- AI systems
- 기타저자
- Princeton University Computer Science
- 기본자료저록
- Dissertations Abstracts International. 85-12B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017161635
■00520250211151424
■006m o d
■007cr#unu||||||||
■020 ▼a9798382806792
■035 ▼a(MiAaPQ)AAI31294505
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aBarnett, Samuel A.▼0(orcid)0000-0001-9612-3096
■24510▼aIncorporating Human Plausibility in Single- and Multi-agent AI Systems
■260 ▼a[Sl]▼bPrinceton University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a103 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-12, Section: B.
■500 ▼aAdvisor: Adams, Ryan P.;Griffiths, Tom.
■5021 ▼aThesis (Ph.D.)--Princeton University, 2024.
■520 ▼aAs AI systems play a progressively larger role in human affairs, it becomes more important that these systems are built with insights from human behavior. In particular, models that are developed on the principle of human plausibility will more likely yield results that are more accountable and more interpretable, in a way that greater ensures an alignment between the behavior of the system and what its stakeholders want from it. In this dissertation, I will present three projects that build on the principle of human plausibility for three distinct applications:(i) Plausible representations: I present the Priority-Adjusted Reply for Successor Representations (PARSR) algorithm, a single-agent reinforcement learning algorithm that brings together the ideas of prioritization-based replay and successor representation learning. Both of these ideas lead to a more biologically plausible algorithm that captures human-like capabilities of transferring and generalizing knowledge from previous tasks to novel, unseen ones.(ii) Plausible inference: I present a pragmatic account of the weak evidence effect, a counterintuitive phenomenon of social cognition that occurs when humans must account for persuasive goals when incorporating evidence from other speakers. This leads to a recursive, Bayesian model that encapsulates how AI systems and their human stakeholders communicate with and understand one another in a way that accounts for the vested interests that each will have.(iii) Plausible evaluation: I introduce a tractable and generalizable measure for cooperative behavior in multi-agent systems that is counterfactually contrastive, contextual, and customizable with respect to different environmental parameters. This measure can be of practical use in disambiguating between cases in which collective welfare is achieved through genuine cooperation, or by each agent acting solely in its own self-interest, both of which result in the same outcome.
■590 ▼aSchool code: 0181.
■650 4▼aComputer science
■650 4▼aComputer engineering
■653 ▼aAI systems
■653 ▼aHuman plausibility
■653 ▼aPriority-Adjusted Reply for Successor Representations
■653 ▼aMulti-agent systems
■690 ▼a0984
■690 ▼a0464
■690 ▼a0800
■71020▼aPrinceton University▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g85-12B.
■790 ▼a0181
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161635▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
